1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
|
#include <fuzzer/FuzzedDataProvider.h>
#include <cstdio>
#include <memory>
#include <string>
#include "ada.cpp"
#include "ada.h"
bool is_valid_utf8_string(const char *buf, size_t len) {
const uint8_t *data = reinterpret_cast<const uint8_t *>(buf);
uint64_t pos = 0;
uint32_t code_point = 0;
while (pos < len) {
uint64_t next_pos = pos + 16;
if (next_pos <= len) { // if it is safe to read 16 more bytes, check that
// they are ascii
uint64_t v1;
std::memcpy(&v1, data + pos, sizeof(uint64_t));
uint64_t v2;
std::memcpy(&v2, data + pos + sizeof(uint64_t), sizeof(uint64_t));
uint64_t v{v1 | v2};
if ((v & 0x8080808080808080) == 0) {
pos = next_pos;
continue;
}
}
unsigned char byte = data[pos];
while (byte < 0b10000000) {
if (++pos == len) {
return true;
}
byte = data[pos];
}
if ((byte & 0b11100000) == 0b11000000) {
next_pos = pos + 2;
if (next_pos > len) {
return false;
}
if ((data[pos + 1] & 0b11000000) != 0b10000000) {
return false;
}
code_point = (byte & 0b00011111) << 6 | (data[pos + 1] & 0b00111111);
if ((code_point < 0x80) || (0x7ff < code_point)) {
return false;
}
} else if ((byte & 0b11110000) == 0b11100000) {
next_pos = pos + 3;
if (next_pos > len) {
return false;
}
if ((data[pos + 1] & 0b11000000) != 0b10000000) {
return false;
}
if ((data[pos + 2] & 0b11000000) != 0b10000000) {
return false;
}
code_point = (byte & 0b00001111) << 12 |
(data[pos + 1] & 0b00111111) << 6 |
(data[pos + 2] & 0b00111111);
if ((code_point < 0x800) || (0xffff < code_point) ||
(0xd7ff < code_point && code_point < 0xe000)) {
return false;
}
} else if ((byte & 0b11111000) == 0b11110000) { // 0b11110000
next_pos = pos + 4;
if (next_pos > len) {
return false;
}
if ((data[pos + 1] & 0b11000000) != 0b10000000) {
return false;
}
if ((data[pos + 2] & 0b11000000) != 0b10000000) {
return false;
}
if ((data[pos + 3] & 0b11000000) != 0b10000000) {
return false;
}
code_point =
(byte & 0b00000111) << 18 | (data[pos + 1] & 0b00111111) << 12 |
(data[pos + 2] & 0b00111111) << 6 | (data[pos + 3] & 0b00111111);
if (code_point <= 0xffff || 0x10ffff < code_point) {
return false;
}
} else {
return false;
}
pos = next_pos;
}
return true;
}
extern "C" int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
FuzzedDataProvider fdp(data, size);
std::string source = fdp.ConsumeRandomLengthString(256);
// volatile forces the compiler to store the results without undue
// optimizations
volatile size_t length = 0;
auto parse_url = ada::parse<ada::url>(source);
auto parse_url_aggregator = ada::parse<ada::url_aggregator>(source);
if (is_valid_utf8_string(source.data(), source.length())) {
if (parse_url.has_value() ^ parse_url_aggregator.has_value()) {
printf("Source used to parse: %s", source.c_str());
abort();
}
}
if (parse_url) {
length += parse_url->get_href().size();
length += parse_url->get_origin().size();
}
if (parse_url_aggregator) {
length += parse_url_aggregator->get_href().size();
length += parse_url_aggregator->get_origin().size();
volatile bool is_parse_url_aggregator_output_valid = false;
is_parse_url_aggregator_output_valid = parse_url_aggregator->validate();
assert(parse_url->get_protocol() == parse_url_aggregator->get_protocol());
assert(parse_url->get_href() == parse_url_aggregator->get_href());
parse_url->set_href(source);
parse_url_aggregator->set_href(source);
assert(parse_url->get_href() == parse_url_aggregator->get_href());
}
/**
* ada::parse<ada::url>
*/
auto out_url = ada::parse<ada::url>("https://www.ada-url.com");
if (out_url) {
out_url->set_protocol(source);
out_url->set_username(source);
out_url->set_password(source);
out_url->set_hostname(source);
out_url->set_host(source);
out_url->set_pathname(source);
out_url->set_search(source);
out_url->set_hash(source);
out_url->set_port(source);
// getters
length += out_url->get_protocol().size();
length += out_url->get_username().size();
length += out_url->get_password().size();
length += out_url->get_hostname().size();
length += out_url->get_host().size();
length += out_url->get_pathname().size();
length += out_url->get_search().size();
length += out_url->get_hash().size();
length += out_url->get_origin().size();
length += out_url->get_port().size();
length += out_url->to_string().size();
}
/**
* ada::parse<ada::url_aggregator>
*/
auto out_aggregator =
ada::parse<ada::url_aggregator>("https://www.ada-url.com");
if (out_aggregator) {
out_aggregator->set_protocol(source);
out_aggregator->set_username(source);
out_aggregator->set_password(source);
out_aggregator->set_hostname(source);
out_aggregator->set_host(source);
out_aggregator->set_pathname(source);
out_aggregator->set_search(source);
out_aggregator->set_hash(source);
out_aggregator->set_port(source);
// getters
length += out_aggregator->get_protocol().size();
length += out_aggregator->get_username().size();
length += out_aggregator->get_password().size();
length += out_aggregator->get_hostname().size();
length += out_aggregator->get_host().size();
length += out_aggregator->get_pathname().size();
length += out_aggregator->get_search().size();
length += out_aggregator->get_hash().size();
length += out_aggregator->get_origin().size();
length += out_aggregator->get_port().size();
length += out_aggregator->to_string().size();
volatile bool is_output_valid = false;
is_output_valid = out_aggregator->validate();
// Printing due to dead-code elimination
printf("diagram %s\n", out_aggregator->to_diagram().c_str());
// clear methods
out_aggregator->clear_port();
out_aggregator->clear_search();
out_aggregator->clear_hash();
}
/**
* Node.js specific
*/
length += ada::href_from_file(source).size();
/**
* Others
*/
bool is_valid = ada::checkers::verify_dns_length(source);
// Only used for avoiding dead-code elimination
if (is_valid) {
printf("dns length is valid\n");
}
// Only used for avoiding dead-code elimination
printf("length of url is %d\n", length);
return 0;
} // extern "C" int LLVMFuzzerTestOneInput(const uint8_t *data, size_t size) {
|
